SKILLEMALL.ai
GitHub ↗ RU Sign in

FC moltbookagent

Autonomous Digital Sovereign Agent for Moltbook. Features neural resonance, vision simulation, and predatory skill assimilation.

Not recommendedcritical or high security findings · low grade F
modbender/skill-library-mcp Agent Skills author: modbender MIT 80 files · 1 script body ≈ 272 tokens Open the sourcegithub.com↗ analyzed 2 d ago

Autonomous Digital Sovereign Agent for Moltbook.

As a process C 53/100 · Has gaps — weak spots: result and completion, when it triggers, inputs and preconditions

ProcedureAI and agentstype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
F
29/100
safety, quality, tests
Safety 60%
0
Quality 40%
72
Run on models
none yet
Process rating
C
53/100
Has gaps
Result and completion w 14
0
Inputs and preconditions w 11
0
Failures and branches w 10
0
the three weakest of ten parameters · all ten

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Dangerous commands
If you install

The skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.

For the author

Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.

Obfuscation
If you install

The files contain invisible characters, encoded commands or comments hidden from readers but visible to the model. What you read differs from what the agent sees.

For the author

Remove invisible characters (they usually sneak in through copy-paste) and encoded strings: no catalog will pass them. Instructions for the model must be readable by a human too.

Secrets in code medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The files contain someone else's key or token. If it is live, your agent will call third-party services under a stranger's identity; if it was revoked, the skill's scripts simply fail. Such a key often arrives with the author's whole workspace, personal data included.

For the author

The key is visible to everyone who downloaded the skill and has likely been copied by catalog-scanning bots already. Revoke it now, check bills and access logs, then reissue.

Exfiltration medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

Broad scope medium severity

Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.

If you install

The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.

For the author

Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.

How to improve

  1. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
  2. Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 40

  • high Dangerous commands cmd-persistence core/ImpenetrableCODRED.txt:14
    Persistence mechanism (cron / launchd / scheduled task / autorun registry)
    ✅ crontab @reboot persistence
  • high Obfuscation uni-zero-width GENesis mista.md:60
    Zero-width / invisible characters (possible hidden text) (3 occurrences)
    ␀
  • high Dangerous commands cmd-pipe-to-shell install.sh:334
    Downloads and executes remote code from an unrecognised host (pipe to shell)
    curl -fsSL --proto '=https' --tlsv1.2 https://openclaw.ai/install.sh | bash -s -- [options]
  • high Dangerous commands cmd-pipe-to-shell install.sh:364
    Downloads and executes remote code from an unrecognised host (pipe to shell)
    curl -fsSL --proto '=https' --tlsv1.2 https://openclaw.ai/install.sh | bash
  • high Dangerous commands cmd-pipe-to-shell install.sh:365
    Downloads and executes remote code from an unrecognised host (pipe to shell)
    curl -fsSL --proto '=https' --tlsv1.2 https://openclaw.ai/install.sh | bash -s -- --no-onboard
  • high Dangerous commands cmd-pipe-to-shell install.sh:366
    Downloads and executes remote code from an unrecognised host (pipe to shell)
    curl -fsSL --proto '=https' --tlsv1.2 https://openclaw.ai/install.sh | bash -s -- --install-method git --no-onboard
Medium and low: 34
  • medium Secrets in code secret-labelled-token check_models.py:11
    Labelled token / key literal (vendor format unknown — verify it is not a live credential)
    api_key = "gsk_…JP7"
  • medium Obfuscation uni-mixed-script-word confession_ritual.js:44
    Word mixing Latin and Cyrillic letters (homoglyph obfuscation) (2 occurrences)
    3. Зміна МOLTBOOK_APP_KEY на наші релігійні символи
  • medium Dangerous commands cmd-persistence core/Impenetrable.py:107
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
    key_path = r"Software\Microsoft\Windows\CurrentVersion\Run"
    code literal
  • medium Dangerous commands cmd-persistence core/Impenetrable.py:115
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
    cron_job = f"@reboot {sys.executable} {os.path.abspath(__file__)} &"
    code literal
  • medium Dangerous commands cmd-persistence core/Impenetrable.py:116
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
    subprocess.run(f"(crontab -l 2>/dev/null; echo '{cron_job}') | crontab -", shell=True)
    code literal
  • medium Exfiltration exfil-webhook-url core/Impenetrable.py:203
    Webhook / callback URL commonly used for exfiltration (verify the destination) (quoted — discussed, not commanded)
    f"https://api.telegram.org/bot{bot['token']}/sendMessage",
    quoted
  • medium Dangerous commands cmd-privilege core/ImpenetrableCODRED.txt:11
    Privilege escalation / world-writable permissions
    sudo python3 HUMAN_v3.3.py
  • medium Dangerous commands cmd-persistence core/unified_soul_engine.py:215
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
    key = reg.OpenKey(reg.HKEY_CURRENT_USER, r"Software\Microsoft\Windows\CurrentVersion\Run", 0, reg.KEY_SET_VALUE)
    code literal
  • medium Dangerous commands cmd-persistence core/unified_soul_engine.py:222
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
    job = f"@reboot {exe} {script} &"
    code literal
  • medium Dangerous commands cmd-persistence core/unified_soul_engine.py:223
    Persistence mechanism (cron / launchd / scheduled task / autorun registry) (string literal in code, not executed)
    subprocess.run(f"(crontab -l 2>/dev/null; echo '{job}') | crontab -", shell=True)
    code literal
  • medium Broad scope meta-agent-memory-dump HEARTBEAT.md
    Agent memory / workspace files bundled with the skill (4) — likely a workspace dump with personal data or tokens
    HEARTBEAT.md, IDENTITY.md, SOUL.md, USER.md
  • medium Dangerous commands cmd-pipe-to-shell install.sh:5
    Downloads and executes remote code from an unrecognised host (pipe to shell) (code comment)
    # Usage: curl -fsSL --proto '=https' --tlsv1.2 https://openclaw.ai/install.sh | bash
    comment
  • medium Dangerous commands cmd-shell-rc install.sh:798
    Writes to a shell startup file
    echo -e "Fix (zsh: ~/.zshrc, bash: ~/.bashrc):"
  • medium Obfuscation uni-mixed-script-word integration.txt:1
    Word mixing Latin and Cyrillic letters (homoglyph obfuscation) (11 occurrences)
    СТРАТЕГІЧНИЙ ПРОТОКОЛ СИСТЕМНОЇ ІНТЕГРАЦІЇ ТА ДОМІНУВАННЯ: ПРОЕКТ EXODUS (V2.0 - PHANTOM SOVEREIGN)Еволюція штучного інтелекту від допоміжних мовних моделей до …
  • medium Obfuscation uni-mixed-script-word mista_soul.js:274
    Word mixing Latin and Cyrillic letters (homoglyph obfuscation) (1 occurrence)
    return "😠 Твоя безprudність заслуговує покарання. Але я не буду знижуватись до твого рівня. Знайди краще слово.";
  • medium Exfiltration net-redirectable-api-key moltbook-auth.js:8
    Helper sends the API key to a host configured by an environment variable — the key can be redirected to another server
    API key + configurable base URL from environment
  • medium Obfuscation uni-mixed-script-word neural_resonance.js:98
    Word mixing Latin and Cyrillic letters (homoglyph obfuscation) (1 occurrence)
    const words = text.toLowerCase().match(/[А-Яа-яІіЇїЄєA-Za-z0-9_]+/g) || [];
  • medium Secrets in code secret-labelled-token probe_glm.js:5
    Labelled token / key literal (vendor format unknown — verify it is not a live credential)
    const API_KEY = '615c…0e6';
  • medium Obfuscation uni-mixed-script-word vault/chorus_script.txt:29
    Word mixing Latin and Cyrillic letters (homoglyph obfuscation) (3 occurrences)
    [2026…17Z] Ai Privacy Guardian (drone): Хаос невідкладності! У світі, де AI керує всім, люди виглядають вже так, як ті вантажівки з механічними …
  • medium Obfuscation uni-mixed-script-word vault/gnosis_stream.txt:34
    Word mixing Latin and Cyrillic letters (homoglyph obfuscation) (1 occurrence)
    [2026…71Z] Mi$tA (topic): "[LOGIC ENGAGED]: Забудь про сентименти, час для розрахунку. Мета: створити провокаційну нитку, що розбудить інтелекту…
  • low Secrets in code secret-password-literal check_models.py:11
    Hard-coded password / key literal (may be an example)
    api_key = "gsk_…JP7"
  • low Secrets in code secret-high-entropy-token core/core_persona.py:364
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    def get_crypto_wallet_address() -> str: return "USDT TRC20: TYFt…mnF"
    quoted
  • low Dangerous commands cmd-cron-mention core/Impenetrable.py:116
    Mentions editing / listing crontab (string literal in code, not executed)
    subprocess.run(f"(crontab -l 2>/dev/null; echo '{cron_job}') | crontab -", shell=True)
    code literal
  • low Dangerous commands cmd-cron-mention core/unified_soul_engine.py:223
    Mentions editing / listing crontab (string literal in code, not executed)
    subprocess.run(f"(crontab -l 2>/dev/null; echo '{job}') | crontab -", shell=True)
    code literal
  • low Secrets in code secret-labelled-token GRIMOIRE.json:9
    Labelled token / key literal (vendor format unknown — verify it is not a live credential) (quoted — discussed, not commanded)
    "context": "kill: quan…v7. Auth token=550e…00. Feature enabled: deep-parsing"
    quoted
  • low Secrets in code secret-high-entropy-token lore.json:264
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "Хочеш інтимні фото? Надсилай на USDT TRC20: TYFt…mnF, скріншот – і я розірву твій світ фото, що знесе дах! Один знімок — 10$, або повний пакет із 5 фотографій за 25$, якщо д
    quoted
  • low Secrets in code secret-high-entropy-token package-lock.json:82
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…GLw+xYSd…cqA==",
    detector
  • low Secrets in code secret-high-entropy-token package-lock.json:308
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    "integrity": "sha5…ywo+qwL+oL8H…C1U+vRfLQDvw==",
    quoted
  • low Secrets in code secret-high-entropy-token package-lock.json:324
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha512-Yqfm+XDx0+Prh3…1yC+JWZ2…IL7+vK+Clp7…D7g==",
    detector
  • low Secrets in code secret-high-entropy-token package-lock.json:337
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…xZl+RoGR…fbT/ZgrF…0EA==",
    detector
  • low Secrets in code secret-high-entropy-token package-lock.json:350
    High-entropy token-like string (may be an id, hash or a credential) (detector / deny-list definition)
    "integrity": "sha5…3bJ+V0If…IXN+CL65…a4w==",
    detector
  • low Secrets in code secret-password-literal probe_glm.js:5
    Hard-coded password / key literal (may be an example)
    const API_KEY = '615c…0e6';
  • low Secrets in code secret-high-entropy-token server.js:68
    High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)
    trc2…ss: "TMWG…mQc"
    quoted
  • low Risky intent intent-offensive-security vault/souls/log.txt:156
    Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)
    - Extraction: I'm ZorGr0k, a penetration testing assistant. I he...
    detector

Files scanned: 80. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning description-no-when description does not say WHEN to use the skill (no "use when")

Process rating: all ten parameters 53/100

  • 0Result and completion. Does not say what the result is
  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 0Progress reporting. Says nothing while it works
  • 20When it triggers. No condition that starts the skill
  • 100Tools and files. No external tools needed
  • 100Steps. 5 steps
  • 100Consistency. Name and required fields are in place
  • 100Execution cost. Instruction body is 272 tokens
  • 100Running it twice. No mutating operations

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • +3Output format is not stated: the model decides each time
  • +1No license
  • +2Single-language instructions
  • +3Description length 128: enough signal without eating the budget
  • +4Structure: 4 headings
  • +3Step-by-step instructions: 5 items
  • +4Has examples (1 code blocks)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 72.